Synchronizing local compiler cache.

.gitattributes

@@ -5825,3 +5825,8 @@ neuronxcc-2.15.141.0+d3cfc8ca/MODULE_4567314586379092116+b64a7507/model.neff fil
 neuronxcc-2.15.141.0+d3cfc8ca/MODULE_17482865381550851151+b64a7507/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.141.0+d3cfc8ca/MODULE_9526574961901883537+b64a7507/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.141.0+d3cfc8ca/MODULE_8089271392344472916+b64a7507/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_120622b3b501e0e834a2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_26502d513f1f857f862b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_4a67e09b982c55e7ac02+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_56746260f3284b6fa940+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_7a7df059e848289de148+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Hermes-3-Llama-3.1-8B/0d4365a2cd0897b2e4f9.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128040, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "NousResearch/Hermes-3-Llama-3.1-8B", "checkpoint_revision": "896ea440e5a9e6070e3d8a2774daf2b481ab425b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Hermes-3-Llama-3.1-8B/9a1318d5b365d5c9462a.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128040, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "NousResearch/Hermes-3-Llama-3.1-8B", "checkpoint_revision": "896ea440e5a9e6070e3d8a2774daf2b481ab425b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 8192, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Hermes-3-Llama-3.1-8B/a6bbbde817f5d81139eb.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128040, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "NousResearch/Hermes-3-Llama-3.1-8B", "checkpoint_revision": "896ea440e5a9e6070e3d8a2774daf2b481ab425b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Hermes-3-Llama-3.1-8B/f0388ec6d1d8a37a6cb5.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128040, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-3-Llama-3.1-8B", "checkpoint_revision": "896ea440e5a9e6070e3d8a2774daf2b481ab425b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/MODULE_120622b3b501e0e834a2+39f12043/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_120622b3b501e0e834a2+39f12043/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b814b2bcdff2c8fb22e22b0dc93bb17b5c9dc464601d01b5c15086c03f29c4
+size 449021

neuronxcc-2.15.128.0+56dc5a86/MODULE_120622b3b501e0e834a2+39f12043/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60762582deaccaee8d2fafc0f253711aaf1e8bc4d0ede5a1c17c5093e19131d9
+size 30188544

neuronxcc-2.15.128.0+56dc5a86/MODULE_26502d513f1f857f862b+39f12043/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_26502d513f1f857f862b+39f12043/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e31c2a5c68635e016295cac480826b2f54d973f3762d39ff981ca48b71ebb7a
+size 449414

neuronxcc-2.15.128.0+56dc5a86/MODULE_26502d513f1f857f862b+39f12043/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb3cee7363f8d8a6be783dded69a0816b7ceb1e72f1ca931ab808bc285ca8a1
+size 6063104

neuronxcc-2.15.128.0+56dc5a86/MODULE_4a67e09b982c55e7ac02+39f12043/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_4a67e09b982c55e7ac02+39f12043/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689117ba138f483a6665fc4bdcaca3b0c6c4d5e9e77f6b8401a2b2c443e5b387
+size 449021

neuronxcc-2.15.128.0+56dc5a86/MODULE_4a67e09b982c55e7ac02+39f12043/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef3cb2e8ace8a75d6fd6dc31de6a70f56364c45beb4787f12b38609c8165a66
+size 30188544

neuronxcc-2.15.128.0+56dc5a86/MODULE_56746260f3284b6fa940+39f12043/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_56746260f3284b6fa940+39f12043/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3178d8c01a52334e6575c7abddd566444d45aae7c1f173cfcef0bfc5d41f3c67
+size 363555

neuronxcc-2.15.128.0+56dc5a86/MODULE_56746260f3284b6fa940+39f12043/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4191c1fb3c02f9ff154d6b7c9c263ebe81189e6e6ba78e4d8bb4a5ed2f6c93f
+size 4127744

neuronxcc-2.15.128.0+56dc5a86/MODULE_7a7df059e848289de148+39f12043/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_7a7df059e848289de148+39f12043/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad38836d539744f28500fd7619a4ea50c3ab8ae98d89eb94adf93978a64f46f
+size 449021

neuronxcc-2.15.128.0+56dc5a86/MODULE_7a7df059e848289de148+39f12043/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff953e6ff2283b2595a1eafe3586a07384dea5510753e86719c2aad9b9fa637
+size 4424704